© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 238949
    Prev
    Next
    INDEX
    Explanations

    14/48 events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اتا
    0.50
    т
    0.50
    ﹁
    0.49
    عب
    0.47
    ANA
    0.47
    ント
    0.46
    вай
    0.46
    Ｉ
    0.46
    غیر
    0.46
    勹
    0.46
    POSITIVE LOGITS
    zechoslovakia
    0.45
     drie
    0.44
     rie
    0.42
    ராட்ச
    0.42
     gents
    0.41
     mehrere
    0.41
     kilka
    0.41
     zehn
    0.41
     regime
    0.41
     ře
    0.41
    Activations Density 0.000%

    No Known Activations